Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/kimsanguine/hplan/pm-enginenpx skills add kimsanguine/hplan --skill pm-enginegit clone --depth 1 https://github.com/kimsanguine/hplanWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kimsanguine/hplan/pm-engine)<a href="https://agentmods.dev/skills/kimsanguine/hplan/pm-engine"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/pm-engine.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00134 | $0.10035 |
| Opus 5 | $0.00067 | $0.05018 |
| Sonnet 5 | $0.00027 | $0.02007 |
| Haiku 4.5 | $0.00013 | $0.01004 |
Grade A, and why
pm-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 824 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Goal
- PM-ENGINE-MEMORY의 TK를 에이전트가 실행 중에 동적으로 참조하여 판단 품질을 의사결정 단계마다 향상시키기
- TK-NNN 단위로 축적된 암묵지를 조직화하여 지식 그래프를 구성하고, 관련 TK를 자동으로 검색/연결되게 관리
- 매일 1개씩 추출되는 새로운 TK를 Instruction에 반영하여 에이전트의 학습 사이클을 자동화
Trigger Gate
Use This Skill When
- 에이전트가 현재 상황과 관련된 PM 판단 기준(TK)이 필요할 때 동적으로 검색하고 싶을 때
- TK를 에이전트 Instruction으로 변환하여 실제 동작에 반영하고 싶을 때
- PM의 경험 기록(TK-001~TK-010 같은 시드)을 기반으로 새로운 TK를 추출하고 저장할 때
- 기존 TK들이 서로 어떻게 연결되는지 확인하거나, 새 TK의 연관성을 매핑할 때
- "이 경험을 TK로 구조화하고 싶어" →
--mode extract - "PM 판단 패턴을 암묵지로 기록하고 싶어" →
--mode extract - "세션에서 발견한 인사이트를 빠르게 저장하고 싶어" →
--mode save "인사이트"사용 - "기술 결정 이유를 PRD와 함께 기록하고 싶어" →
--mode save-decision - "프로젝트의 주요 기술 결정 중 미기록된 것을 찾고 싶어" →
--mode index-codebase
Route to Other Skills When
- "TK를 구조화해서 라이브러리에 저장하고 싶어" → pm-engine --mode extract 사용
- "이 TK가 의사결정에 어떻게 쓰이는지 실제 사례를 보고 싶어" → pm-engine --mode decide의 패턴 라이브러리 참조
- "에이전트 Instruction을 새 TK를 기반으로 업데이트하고 싶어" → deliver의 agent-setup, prd 스킬 사용
- "TK를 기반으로 비용 시뮬레이션이나 시나리오 분석을 하고 싶어" → discover의 cost-sim, opp-tree 사용
- "에이전트 실행 중 예측 vs 실측 deviation 을 TK 후보로 자동 추출" → sprint --step retro → /pm-tacit-from-retro 로 자동 promote
Note:
--mode save는 다른 스킬로 라우팅하지 않고 직접 TK 항목을 저장한다.
Boundary Checks
- PM-ENGINE-MEMORY는 "실전 경험 기반"이므로, 일반 LLM 지식과 항상 충돌할 수 있음 → 충돌 시 TK 우선
- TK가 충분하지 않은 영역(새 제품, 새 시장)에서는 TK만 믿지 말고 데이터 검증 필수
- TK의 활성화/비활성화 조건을 항상 확인 → 조건을 무시한 TK 적용은 오류
--mode save — 빠른 인사이트 저장
세션 중 발견한 인사이트를 TK 추출 플로우 없이 즉시 저장한다.
사용법
/pm-engine --mode save "인터뷰에서 B2B 고객은 ROI 계산보다 리스크 제거를 더 원함"
저장 형식
PM-ENGINE-MEMORY.md 맨 끝에 다음 형식으로 추가:
## TK-QUICK-[YYMMDDHHmm]: [인사이트 제목 자동 추출]
- **날짜**: YYYY-MM-DD
- **출처**: [세션/컨텍스트 — 사용자가 제공하지 않으면 "직접 관찰"로 기록]
- **내용**: [인사이트 전문]
- **적용 가능 상황**: [인사이트에서 추론]
- **태그**: #quick-save
> ⚠️ TK-QUICK은 정식 TK-NNN 검토 전 임시 항목입니다. `/pm-engine --mode extract`로 정식 등록하거나 삭제하세요.
동작 규칙
PM-ENGINE-MEMORY.md없으면 자동 생성 후 저장- 같은 내용 중복 감지 (첫 20자 매칭) → 중복 경고 후 저장 여부 확인
- 저장 후 "TK-QUICK-[ID] 저장됨 —
/pm-engine --mode extract로 정식 등록 가능" 출력
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 824 lines · 134 tokens per session scan A c36d56032173
pm-engine is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 18d ago), licensed MIT. It adds 134 tokens to every session and 10,035 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
alive-bundle
Create, manage, and graduate bundles -- the unit of focused work within a walnut.
user-story-generator
Transforms requirements into user stories with Given/When/Then acceptance criteria ready for sprint planning and Jira. Use when user needs to write user stories, create Jira tickets, define acceptance criteria, or says "user stories", "acceptance criteria", "sprint backlog", "Jira tickets", "as a user I want"…
ambiguity-resolver
Structures a brief HANDED DOWN by a stakeholder (boss, exec, another team) into a one-page problem statement with scope boundaries and a named decision owner. Use when the PM says "мне спустили задачу", "I've been asked to look into Y", "руководство хочет X", "CEO попросил разобраться" — a request the PM didn't…
checkpoint-backlog
Checkpoint the ended Claude Code sessions waiting in subrosa's queue. Reads the pending-checkpoint queue and, for each queued past session, extracts durable facts into that project's memory (leaf files + facts database + regenerated MEMORY.md), then clears it from the queue. Run it at session start when there's a…
contract-testing-flywheel
Generate a structured onboarding backlog — in Jira, GitHub Issues/Projects, Azure DevOps, or as a manual markdown export — that drives a development team from zero to publishing both consumer and provider contract tests. Use when the user invokes /contract-testing-flywheel or asks to "kick off contract testing for a…
prime
Initialize a working session. Loads full workspace context (personal info, business, strategy, current data, pipeline, key contacts, datastore index), runs CRM and sync health checks, surfaces what needs attention, and lists available skills with recommendations for the day. Use at the start of every working session.…